memory

Persist important outcomes from this step to long-term storage with automatic forgetting curve.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agentsociety/packages/agentsociety2/agentsociety2/agent/skills/memory/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured, with a clear write workflow, concrete formats and commands, and clean progressive disclosure to real bundle files. The main weakness is mild verbosity in the conceptual framing sections that adds tokens without proportional value.

Suggestions

Trim the 'Architecture (conceptual) > 1. Working context (implicit)' section and the closing justificatory prose (e.g., 'without pretending the simulation has exact human neural memory'), which restate concepts Claude already knows.

Consider moving the detailed ACT-R activation derivation and decay-rule tables into the existing references/research_basis.md, leaving SKILL.md with the operational summary and a pointer.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and dense (formulas, tables, field specs, JSON examples), but it retains conceptual justification prose (e.g., the 'implicit working context' layer and the closing 'without pretending the simulation has exact human neural memory') that explains things Claude already knows and could be tightened.	2 / 3
Actionability	It provides a copy-paste JSON entry format, a concrete workspace_write invocation with arguments, and an executable maintenance command with flags and environment-variable defaults — fully actionable and copy-paste ready.	3 / 3
Workflow Clarity	The numbered 'How to Write' sequence is unambiguous, with an explicit protective guard ('first workspace_read ... then append' to avoid overwrite loss), a decision gate ('If nothing notable happened, call done immediately'), and a when-to-write/skip checklist serving as a validation checkpoint.	3 / 3
Progressive Disclosure	The SKILL.md serves as an overview that signals one-level-deep, real bundle files — 'references/research_basis.md' for the research basis and 'scripts/memory_maintenance.py' for the maintenance logic — with content appropriately split and easy to navigate; both referenced paths exist in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

35%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear single action and a distinguishing feature, but lacks natural trigger terms and any explicit "when to use" guidance. Adding a user-facing trigger clause and common-sense keywords like "memory" or "remember" would materially improve it.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should persist a memory (e.g., after a meaningful interaction, discovery, or notable state change).

Include natural trigger terms users would say — 'remember', 'memory', 'forget', 'recall' — rather than only technical phrasing like 'long-term storage' and 'forgetting curve'.

Optionally name a second concrete capability (e.g., retrieve/search past memories) to raise specificity from a single action to multiple distinct actions.

Dimension	Reasoning	Score
Specificity	Names one concrete action ("Persist important outcomes from this step to long-term storage") plus a feature ("automatic forgetting curve"), but does not list multiple distinct concrete actions as required for a 3.	2 / 3
Completeness	It answers the "what" (persist outcomes to long-term storage with forgetting) but provides no explicit "Use when..." trigger; "from this step" only implies the when, so completeness is capped at 2.	2 / 3
Trigger Term Quality	It uses technical jargon ("long-term storage", "forgetting curve") and contains no natural user-facing terms such as "memory", "remember", or "forget" that a user would actually say when needing this skill.	1 / 3
Distinctiveness Conflict Risk	The forgetting-curve framing gives it a distinct niche, but "persist outcomes to long-term storage" is generic enough to overlap with general state or storage skills.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: XiaoLuoLYG/GOD
Path: agentsociety/packages/agentsociety2/agentsociety2/agent/skills/memory/SKILL.md
Commit: 4fd5cfc

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.